Open Source

AnythingLLM

Private AI app for chatting with documents, with agents and local models

Is AnythingLLM open source?

Yes. AnythingLLM is open source software released under the MIT license and developed by Mintplex Labs. The source code is public in its official repository.

Advertisement

Overview

AnythingLLM is a free and open source AI application from Mintplex Labs, built around one common need: asking questions about your own documents. You drop files into a workspace, and AnythingLLM indexes them so a language model can answer with references to the source passages, a technique usually called retrieval-augmented generation (RAG).

It runs locally by default. A built-in engine can run open-weight models on your CPU or GPU, or you can connect it to a local server such as Ollama or to cloud providers such as OpenAI and Anthropic. AnythingLLM comes in two forms: a desktop app for Windows, macOS, and Linux, and a Docker version for servers. The Docker version adds multi-user support with permissions and an embeddable chat widget for websites.

Beyond document chat, AnythingLLM includes AI agents that can browse the web and use tools, a no-code agent builder, support for the Model Context Protocol (MCP), scheduled tasks that run prompts on a timetable, and a developer API. The project is MIT-licensed.

Key Features

  • Chat with your documents — Workspaces that index your files and answer with source citations
  • Local by default — A built-in local model engine, plus support for Ollama and other runners
  • Many providers — Works with popular open and closed model providers when you want them
  • Agents and MCP — Agents that use tools, a no-code agent builder, and MCP compatibility
  • Scheduled tasks — Run prompts and agent tasks on a recurring schedule
  • Desktop or server — Single-user desktop app, or a Docker server with multi-user accounts and an embeddable widget

Use Cases

  • Private document Q&A — Search and summarize contracts, notes, manuals, or research papers locally
  • Team knowledge base — A self-hosted assistant over shared documents, with per-user permissions
  • Website support chat — Embed a chat widget backed by your own documentation (Docker version)
  • Automations — Scheduled summaries, reports, and agent tasks

Who It’s For

AnythingLLM suits people and teams who want an AI assistant grounded in their own documents without sending those documents to a cloud service. The desktop app needs no setup beyond installing it; the Docker version is for teams that want a shared server. It’s free under the MIT license.

Advertisement

This is a free alternative to: Claude

Frequently Asked Questions

What is the difference between the desktop and Docker versions?

The desktop app is a single-user application for Windows, macOS, and Linux. The Docker version runs as a server and adds multi-user accounts with permissions and an embeddable chat widget for websites.

Does AnythingLLM need an internet connection?

No. It runs locally by default and includes a built-in engine for local models; you only need a connection to download models or if you choose a cloud provider.

Is AnythingLLM free?

Yes. AnythingLLM is free and open source under the MIT license.

Similar software: AI Assistants

Jan

Desktop AI chat app that runs models locally or connects to cloud APIs

Jan is a free, Apache-2.0 desktop app for chatting with AI models that run on your own computer, with optional connections to cloud providers.

Open Source Apache-2.0

LibreChat

Self-hosted AI chat app for teams, with many model providers

LibreChat is a free, MIT-licensed, self-hosted AI chat app with multi-user accounts, agents, and support for Claude, OpenAI, Google, and local models.

Open Source MIT

llama.cpp

Lightweight C/C++ engine for running LLMs on local hardware

llama.cpp is an MIT-licensed C/C++ engine for running LLMs locally on CPUs and GPUs, with a command-line chat tool and an OpenAI-compatible server.

Open Source MIT

Ollama

Run open-weight language models on your own computer

Ollama is a free, MIT-licensed tool for downloading and running open-weight LLMs locally, with a command line and an API other apps connect to.

Open Source MIT

Claude

Anthropic's AI assistant for writing, analysis, and coding

Claude is Anthropic's proprietary AI assistant for writing, analysis, research, and coding, offered on the web, desktop, and mobile with free and paid plans.

Proprietary

Open WebUI

Self-hosted web interface for local and cloud AI models

Open WebUI is a self-hosted web interface for AI models that works with Ollama and OpenAI-compatible APIs, under a source-available license.

Source Available Source-available